Training in progress, step 160000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6ca6f24dcb89d2b5b321d41377d7112797ffe1d907f15ddff7ba7e26609c862
+oid sha256:a7fa6f67a02b92595e2aff826fe56cab9b750c0aa9eed74a0c077457f9526a38
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4cd57564a779ce9b253560bee2c5cd0e86bb9d45deec93038af06a21499a13
+oid sha256:377f17dd91bef1f8d76bf027ee815cc42fde00afa68776f28a01f3707681243e
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fae3b17a22413cb3757589f57743e787359e0022772ac1abcd8cd137a4f47d67
+oid sha256:9987290a679306f1b084feec0755691092b1d64ddfc7e54de33d1d15f38b37c5
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a779f8fc855d59bcbf291b4cc6b19be7fee9321eb3062f5a2a4c0cebbb9c9578
+oid sha256:e3930873c7aebc048e1e6b5707a188d1d16da050c73fd5a40451efe67b05447a
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b690234daa5d8c7710fe7be510d329d20ff0051c4744ffca45867ea3553623e
+oid sha256:5e66b144627191cd9907774cddaa716b9a3469498c3635098f787cc03994045a
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42a7533496fd3447c3098c72eeb99bc915be9c71a99c7b280c1c6731f19f5133
+oid sha256:467cacbc42e6b7a1aca96dfbbc644355c389f0ee7689457651e4e2a25df79552
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39883cc54bbec8fad581d8040cd06ed3b456d464ef56b30767c2b26d32316b88
-size 14567
+oid sha256:62dfde7cdd3982ed20c005df1890f27c27f2ad9af1961cd883bd47b05ccd4020
+size 14439

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a09d63ee9a8f047626f54ecfd465d1f3475fbfb179597785b1c98b6cb830f2d
+oid sha256:bcbb58a56a3d2cf5b2ed3ab5c08c634b6d8951e1d9246f641494be97ef58199d
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c16621f2d614cd323b166e84be0e313d4e55c720c949cc61553843d3fcddcc8
-size 14439
+oid sha256:7ae31e4239cb266a5df3399c9d9ccb8e2372ff9d2c418e64e941930de1c56237
+size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2acd8d931b1baaa8c54719beb8cd5cf9a1180f13f5175d45461cfed4154f4fc9
+oid sha256:c129c447b52f4655050576e211e6a16cffe6c0990663b13474ab0efd7745497f
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09454c2cc8aac6faf99c7970cf8bec57b59b683887c6bb291c3a0936d0e7d0d
+oid sha256:8bc0c53c979a7805930dacd44e26c88894a437860c12a8b9fd2b0695ce7c583e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.595729035816048,
-  "global_step": 150000,
+  "epoch": 4.902110971537118,
+  "global_step": 160000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3006,11 +3006,211 @@
       "eval_samples_per_second": 1935.344,
       "eval_steps_per_second": 30.965,
       "step": 150000
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 0.000252852507335803,
+      "loss": 0.357,
+      "step": 150500
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 0.0002524981166865307,
+      "loss": 0.3569,
+      "step": 151000
+    },
+    {
+      "epoch": 4.63,
+      "eval_loss": 0.785658597946167,
+      "eval_runtime": 0.5353,
+      "eval_samples_per_second": 1868.045,
+      "eval_steps_per_second": 29.889,
+      "step": 151000
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 0.00025214265981347487,
+      "loss": 0.3565,
+      "step": 151500
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 0.000251786140603855,
+      "loss": 0.3562,
+      "step": 152000
+    },
+    {
+      "epoch": 4.66,
+      "eval_loss": 0.7895671129226685,
+      "eval_runtime": 0.5212,
+      "eval_samples_per_second": 1918.71,
+      "eval_steps_per_second": 30.699,
+      "step": 152000
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 0.00025142856295650795,
+      "loss": 0.3564,
+      "step": 152500
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 0.0002510699307818457,
+      "loss": 0.3561,
+      "step": 153000
+    },
+    {
+      "epoch": 4.69,
+      "eval_loss": 0.7849823832511902,
+      "eval_runtime": 0.5118,
+      "eval_samples_per_second": 1954.042,
+      "eval_steps_per_second": 31.265,
+      "step": 153000
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 0.00025071024800181214,
+      "loss": 0.356,
+      "step": 153500
+    },
+    {
+      "epoch": 4.72,
+      "learning_rate": 0.0002503495185498405,
+      "loss": 0.3559,
+      "step": 154000
+    },
+    {
+      "epoch": 4.72,
+      "eval_loss": 0.779691755771637,
+      "eval_runtime": 0.5352,
+      "eval_samples_per_second": 1868.349,
+      "eval_steps_per_second": 29.894,
+      "step": 154000
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 0.00024998774637081044,
+      "loss": 0.3561,
+      "step": 154500
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 0.00024962493542100443,
+      "loss": 0.3557,
+      "step": 155000
+    },
+    {
+      "epoch": 4.75,
+      "eval_loss": 0.7861126661300659,
+      "eval_runtime": 0.519,
+      "eval_samples_per_second": 1926.643,
+      "eval_steps_per_second": 30.826,
+      "step": 155000
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 0.0002492610896680649,
+      "loss": 0.3554,
+      "step": 155500
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 0.00024889621309095067,
+      "loss": 0.3554,
+      "step": 156000
+    },
+    {
+      "epoch": 4.78,
+      "eval_loss": 0.7840675115585327,
+      "eval_runtime": 0.525,
+      "eval_samples_per_second": 1904.845,
+      "eval_steps_per_second": 30.478,
+      "step": 156000
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 0.00024853030967989366,
+      "loss": 0.3549,
+      "step": 156500
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 0.00024816338343635485,
+      "loss": 0.3552,
+      "step": 157000
+    },
+    {
+      "epoch": 4.81,
+      "eval_loss": 0.776941180229187,
+      "eval_runtime": 0.5336,
+      "eval_samples_per_second": 1874.176,
+      "eval_steps_per_second": 29.987,
+      "step": 157000
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 0.0002477954383729809,
+      "loss": 0.3548,
+      "step": 157500
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 0.00024742647851355997,
+      "loss": 0.3548,
+      "step": 158000
+    },
+    {
+      "epoch": 4.84,
+      "eval_loss": 0.7874701023101807,
+      "eval_runtime": 0.5123,
+      "eval_samples_per_second": 1952.132,
+      "eval_steps_per_second": 31.234,
+      "step": 158000
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 0.0002470565078929781,
+      "loss": 0.3548,
+      "step": 158500
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 0.00024668553055717465,
+      "loss": 0.3548,
+      "step": 159000
+    },
+    {
+      "epoch": 4.87,
+      "eval_loss": 0.7873478531837463,
+      "eval_runtime": 0.5309,
+      "eval_samples_per_second": 1883.499,
+      "eval_steps_per_second": 30.136,
+      "step": 159000
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 0.0002463135505630984,
+      "loss": 0.3548,
+      "step": 159500
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 0.00024594057197866283,
+      "loss": 0.356,
+      "step": 160000
+    },
+    {
+      "epoch": 4.9,
+      "eval_loss": 0.7846257090568542,
+      "eval_runtime": 0.5192,
+      "eval_samples_per_second": 1926.096,
+      "eval_steps_per_second": 30.818,
+      "step": 160000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 4.792275129809597e+21,
+  "total_flos": 5.111762268584097e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4cd57564a779ce9b253560bee2c5cd0e86bb9d45deec93038af06a21499a13
+oid sha256:377f17dd91bef1f8d76bf027ee815cc42fde00afa68776f28a01f3707681243e
 size 102501541